Puyang Zhao

Puyang Zhao

Ph.D. student in Biostatistics at UTHealth

Posts by Collection

portfolio

publications

Research on Prediction of Solar Power Considering the Methods of Statistical and Machine Learning ā€“ Based on the Data of Australian Solar Power Market

Published in IOP conference, 2022

The results show that the regression model with correlated errors is better than the machine learning-based LSTM algorithm, which is based on the differential MSE performance, and can accurately predict solar power generation.

Recommended citation: Zhao, P., & Tian, W. (2022, June). Research on prediction of solar power considering the methods of statistical and machine learningā€“based on the data of Australian solar power market. In IOP Conference Series: Earth and Environmental Science (Vol. 1046, No. 1, p. 012006). IOP Publishing. https://iopscience.iop.org/article/10.1088/1755-1315/1046/1/012006/pdf

An Attention-based Long Short-Term Memory Framework for Detection of Bitcoin Scams

Published in 2022 International Conference on High Performance Big Data and Intelligent Systems (HDIS), 2022

A novel Attention-based Long Short-Term Memory (A-LSTM) method is proposed for the classiļ¬cation problem to determine whether a transaction is involved in Ponzi schemes or other cyber scams, or is a non-scam transaction.

Recommended citation: Zhao, P., Tian, W., Xiao, L., Liu, X., & Wu, J. (2022, December). An Attention-based Long Short-Term Memory Framework for Detection of Bitcoin Scams. In 2022 International Conference on High Performance Big Data and Intelligent Systems (HDIS) (pp. 21-26). IEEE. https://arxiv.org/pdf/2210.14408.pdf

DiGAN Breakthrough: Advancing Diabetic Data Analysis with Innovative GAN-Based Imbalance Correction Techniques

Published in Computer Methods and Programs in Biomedicine Update, 2024

Breakthrough in Diabetes Data Analysis: DiGAN represents a breakthrough approach in the field of medical diagnostics, especially in diabetes classification.

Recommended citation: P. Zhao, X. Liu, Z. Yue et al., DiGAN Breakthrough: Advancing diabetic data analysis with innovative GAN-based imbalance correction techniques, Computer Methods and Programs in Biomedicine Update (2024), doi: https://doi.org/10.1016/j.cmpbup.2024.100152. https://doi.org/10.1016/j.cmpbup.2024.100152.

CENN: Capsule-Enhanced Neural Network with Innovative Metrics for Robust Speech Emotion Recognition

Published in Knowledge-Based Systems, 2024

This paper introduces a groundbreaking Capsule-enhanced neural network (CENN) that significantly advances the state of SER through a robust and reproducible deep learning framework.

Recommended citation: Huiyun Zhang, Heming Huang, Puyang Zhao, Xiaojun Zhu, Zhenbao Yu, CENN: Capsule-Enhanced Neural Network with Innovative Metrics for Robust Speech Emotion Recognition, Knowledge-Based Systems (2024). https://www.sciencedirect.com/science/article/pii/S095070512401133X

Sparse Temporal Aware Capsule Network for Robust Speech Emotion Recognition

Published in Engineering Applications of Artificial Intelligence, 2025

This paper introduces a novel Sparse Temporal-Aware Capsule Network (STACN) architecture designed to enhance the accuracy and reliability of speech emotion recognition systems.

Recommended citation: Zhang, H., Huang, H., Zhao, P., & Yu, Z. (2025). Sparse Temporal Aware Capsule Network for Robust Speech Emotion Recognition. Engineering Applications of Artificial Intelligence. https://doi.org/10.1016/j.engappai.2025.110060

Applied statistical methods for identifying features of heart rate that are associated with nicotine vaping

Published in The American Journal of Drug and Alcohol Abuse, 2025

This paper introduces a series of statistical methods to analyze heart rate data and identify features associated with nicotine vaping.

Recommended citation: Zhao, P., Yang, J.J., & Buu, A. (2025). Applied statistical methods for identifying features of heart rate that are associated with nicotine vaping. The American Journal of Drug and Alcohol Abuse. https://doi.org/10.1080/00952990.2024.2441868 https://doi.org/10.1080/00952990.2024.2441868

Reproducible and generalizable speech emotion recognition via an Intelligent Fusion Network

Published in Biomedical Signal Processing and Control, 2025

We propose the Intelligent Fusion Network (IFN), a novel architecture combining dual attention, feature refinement, and multiplicative fusion to enhance speech emotion recognition (SER) performance and reproducibility. Extensive experiments across six benchmark datasets demonstrate IFNā€™s superior accuracy and generalizability, establishing it as a reliable and effective solution for advancing human-computer interaction.

Recommended citation: Zhang, H., Zhao, P., Tang, G., Li, Z., & Yuan, Z. (2025). Reproducible and generalizable speech emotion recognition via an Intelligent Fusion Network. Biomedical Signal Processing and Control, 109, 107996. https://www.sciencedirect.com/science/article/abs/pii/S1746809425005075

talks

teaching

Assistant Instructor I

Undergraduate course, BNU-HKBU United International College, Department of Statistics, 2021

Participated in teaching and tutoring for five subjects: Calculus I (1002), Calculus I (1004), Logistics, Network and Transportation Models, Data Analysis for Business (1001). Prepared lesson plans, follow-up exercises, homework assignments, unit tests, and final examinations.

Teaching Assistant

Graduate course, The University of Texas Health Science Center at Houston, Department of Biostatistics and Data Science, 2024

  • Led STATA tutorials and instructional sessions for PH 1700 Intermediate Biostatistics and PH 1976 Data Analytics and Predictions.
  • Developed comprehensive solution guides and evaluated student performance through assignments, tests, and examinations.
  • Provided individualized consultations during office hours, helping students master complex statistical concepts and programming skills.
  • Supported course instruction by creating supplementary learning materials and grading assessments.